用机器学习估算图像创造力：基于新颖性、惊喜度与唤醒度三维度框架
Estimating Image Creativity
这篇论文把"这张图有没有创意"这种主观判断变成了可计算的分数：先预测新颖性、惊喜度、唤醒度三个维度，再合成总分，结果和人类评分统计等价。做 AIGC 图像评估或内容筛选的团队可以直接参考它的实验设计，标注数据是通过 Amazon Mechanical Turk 收的，方法可复现。
一项发表于 arXiv 的研究提出估算图像感知创造力的新框架，核心是把创造力拆解为新颖性（novelty）、惊喜度（surprise）和唤醒度（arousal）三个心理学维度。研究团队在 Amazon Mechanical Turk 上开展受控人类实验收集标注数据，训练监督式机器学习模型分别预测一张图像在三个维度上的强度，再将维度得分组合成最终的创造力分数。
实验结果显示，模型给出的创造力估算分数与人类评分在统计上等价，即两者差异不具显著性。研究贡献包括三点：验证了三个心理学创造力维度对图像创造力评估的有效性；构建了自动预测三维度强度的模型；以及开发了从维度强度映射到创造力分数的机器学习模型。
这项工作的意义在于把看似主观的创造力判断转化为可计算的预测任务，可用于生成式图像的自动评估、素材筛选等场景。论文同时给出了验证方法准确性与局限性的实验设计，方便后续研究复现和比较。
Estimating Image Creativity
What makes an image creative? Although this may seem like a highly subjective decision, research in psychology suggests that creativity may be based on a set of fundamental creativity dimensions such as novelty, surprise, and arousal. A deeper understanding of image creativity can benefit both research and practical applications. Exploring how human viewers use creativity dimensions to evaluate image creativity may allow us to predict a target image's human-rated creativity automatically. We present a novel framework to estimate the perceived creativity of an image by: (1) predicting the strengths of an image's novelty, surprise, and arousal creativity dimensions, and (2) combining the creativity dimension strengths to estimate an image creativity score. Controlled human-subject experiments were conducted on Amazon Mechanical Turk to collect data to train supervised machine learning models to estimate an image's strengths on the three creativity dimensions. A final machine learning model takes the predicted dimension strengths as input to produce an estimated image creativity score. Results showed that our estimated creativity scores are statistically equivalent to human ratings of creativity for the images we tested. The novel contributions of our research are: (1) identification and validation of three psychological creativity dimensions used to estimate image creativity; (2) supervised machine learning models to automatically estimate novelty, surprise, and arousal strengths for an input image; (3) a supervised machine learning model to predict a creativity score from novelty, surprise, and arousal strengths for an input image, and (4) experimental methods to confirm the accuracy, advantages, and limitations of our approach.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include arXiv, 图像创造力, 机器学习, 心理学.
Source attribution: curated from arXiv cs.LG (@Nisan Chhetri, Christopher G. Healey, Sina Baghbanijam).